NEURAL NETWORK &THEIR APPLICATIONS BY DAKSHIMA SHARMA COMPUTER SCIENCE ENGINEERING 3RD YEAR
INTRODUCTION• Models of the brain and nervous system• Process information much more like the brain than a serial computer• Very simple principles and complex behaviours.• An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by biological nervous systems.• It is composed of a large number of highly interconnected processing elements called neurons.• An ANN is configured for a specific application, such as pattern recognition or data classification
NEURAL SYSTEMBIOLOGICAL ARTIFICIAL• They are made up of real biological • They are composed of interconnecting neurons that are connected or functionally artificial neurons (programming related in a nervous system . constructs that mimic the properties• In the field of neuroscience, they are often of biological neurons) for solving identified as groups of neurons that artificial intelligence problems without perform a specific physiological function creating model of real system. in laboratory analysis. • The algorithms abstract away the biological complexity by focusing on the most important information. The goal of artificial neural networks human- like, predictive ability.
WHY TO USE ANN???• ability to derive meaning from complicated or imprecise data• extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques• Adaptive learning• Real Time Operation• Conventional computers use an algorithmic approach, but neural networks works similar to human brain and learns by example.
ARTIFICIAL NEURAL NETWORKS(ANN)-: • Also called simulated neural network (SNN), is an interconnected group of natural or artificial neurons that uses a mathematical or computational model for information processing based on a connectionistic approach to computation. • In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network. • ANNs incorporate the two fundamental components of biological neural nets:1. Neurones (nodes)2. Synapses (weights)
Analogy between ANN and NNN NODE V/S NEURON & WEIGHT V/S SYNAPSE
BASICS OF NEURAL SYSTEM1 A set of synapses or connecting links, each link characterized by a weight: W1, W2, …, Wm2 An adder function (linear combiner) which computes the weighted sum of the inputs: m u wjxj j 13 Activation function (squashing function) for limiting the amplitude of the output of the neuron. y (u b)
ARCHITECTURE OF NEURALSYSTEMFEED FORWARD :Neurons are arranged in acyclic layer Output and this arrangement can be of: Input layer layer of of source nodes neuron 3-4-2 Network s 1)- Single layer Input Output layer layer2)- Multilayer Hidden Layer
FEED FORWARD ANN• Information flow is unidirectional ▫ Data is presented to I nput layer ▫ Passed on to Hidden Layer ▫ Passed on to Output layer• Information is distributed• Information processing is parallel
RECURRENT ANN▫ Nodes connect back to other nodes or themselves z-1▫ Information flow is multidirectional▫ Sense of time and memory of BLUE-input previous state(s) z-1 BROWN-hidden GREEN-outputunit delay operator z-1 impliesdynamic system z-1
APPLICATIONS FINGERPRINT RECOGNITION Image edge Ridge Thinin Feature classifi acquisiti detecti extractio g extracti cation on on n on• Image Acquisition: the acquired image is digitalized into 512x512 image with each pixel assigned a particular gray scale value (raster image).• Edge Detection and Thinning: these are preprocessing of the image , remove noise and enhance the image.
FINGERPRINT RECOGNITIONSYSTEM• Feature extraction: this the step where we point out the features such as ridge bifurcation and ridge endings of the finger print with the help of neural network.• Classification: here a class label is assigned to the image depending on the extracted features.
PREPROCESSING SYSTEMThe first phase is to capture a imageThe image is captured using TIR .The image is stored as a two dimensionalarray of 512x512 size, each element ofarray representing a pixel and assigned agray scale value from 256 gray scalelevels. Image is captured ,noise is removed using.Edge detection: the edge is defined wherethe gray scale levels changes greatly.also, orientation of ridges is determinedfor each 32x32 block of pixels using grayscale gradient.Ridge extraction: are extracted using thefact that gray scale value of pixels aremaximum along the direction normal to theridge orientation.
PREPROCESSING SYSTEM Thinning: the extracted ridges are converted into skeletal structure in which ridges are only one pixel wide. thinning should not- Remove isolated as well as surrounded pixel. Break connectedness. Make the image shorter.• Multilayer perceptron network of three layers is trained to detect minutiae in the thinned image. The first layer has nine perceptrons The hidden layer has five perceptrons The output layer has one perceptron. The network is trained to output ‘1’ when the input window is centered at the minutiae and it outputs ‘0’ when minutiae are not present.
FEATURE EXTRACTION• Trained neural networks are used to analyze the image by scanning the image with a 3x3 window.• To avoid falsely reported features which are due to noise – The size of scanning window is increased to 5x5 If the minutiae are too close to each other than we ignore all of them.
FACE RECOGNITION90% accurate learning head pose, and recognizing 1-of-20 faces
OTHER APPLICATIONSCharacter Recognition - The idea of character recognition has become veryimportant as handheld devices like the Palm Pilot are becoming increasingly popular.Neural networks can be used to recognize handwritten characters.Image Compression - Neural networks can receive and process vast amounts ofinformation at once, making them useful in image compression. With the Internetexplosion and more sites using more images on their sites, using neural networks forimage compression is worth a look.
OTHER APPLICATIONSStock Market Prediction - The day-to-day business of the stock market is extremelycomplicated. Many factors weigh in whether a given stock will go up or down on anygiven day. Since neural networks can examine a lot of information quickly and sort it allout, they can be used to predict stock prices.Travelling Salesman Problem- Interestingly enough, neural networks can solve thetravelling salesman problem, but only to a certain degree of approximation.Medicine, Electronic Nose, Security, and Loan Applications - These are someapplications that are in their proof-of-concept stage, with the acceptance of a neuralnetwork that will decide whether or not to grant a loan, something that has alreadybeen used more successfully than many humans.Miscellaneous Applications - These are some very interesting (albeit at times a littleabsurd) applications of neural networks.
SUMMARY• Neural network solutions should be kept as simple as possible.• For the sake of the gaming speed neural networks should be applied preferably off- line.• A large data set should be collected and it should be divided into training, validation, and testing data.• Neural networks fit as solutions of complex problems.• A pool of candidate solutions should be generated, and the best candidate solution should be selected using the validation data.• The solution should be represented to allow fast application.